gvc_agora_opentargets

Setup environment

library(tidyverse)
library(janitor)
library(broom)
library(readxl)
library(jsonlite)

library(gprofiler2)

theme_set(theme_bw())

set.seed(666)

Read and prep data

GVC

Genes within 1Mb window of (each side of?) GVC loci from Fanny:

gvc <- read_xlsx("GVC_1Mb_comparison_050224.xlsx") |>
  clean_names() |> 
  separate(gene_id, c("gene_id", "version")) |>
  select(-version, -agora_nominated_list, -opentarget_info)

gvc

gvc.genes <- gvc |> distinct(gene_id, .keep_all = TRUE) |> select(gene_id, gene_symbol) |> arrange(gene_symbol)

gvc.genes

Agora

Alzheimer’s disease gene prioritization scores from Agora (see also related journal article):

ago1 <- read_json("syn25741025.overall_scores.json", simplifyVector = TRUE) |> as_tibble()

ago1

Alzheimer’s disease genes (AMPAD Agora) from Fanny:

ago2 <- read_csv("AMPAD_agora_032124_gene-list.csv")
ago2

ago <- ago1 |> filter(hgnc_symbol %in% ago2$`Gene Symbol`)

OpenTargets

Alzheimer’s disease gene prioritization scores from OpenTargets:

ot <- read_tsv("OT-MONDO_0004975-associated-targets-6_4_2024-v24_03.tsv", show_col_types = FALSE, na = "No data")

ot

Add Ensembl Gene IDs (WTF!):

otcols <- colnames(ot)
otensg <- gconvert(
  query = ot$symbol,
  organism = "hsapiens",
  target= "ENSG",
  mthreshold = Inf,
  filter_na = TRUE) |> 
  mutate(input_number = as.character(input_number)) |>
  left_join(ot |> rownames_to_column(var = "input_number"), by = "input_number") |> 
  select(ensembl_gene_id = target, otcols)

otensg

Annotate GVC genes with Agora and OpenTargets scores

sum(gvc.genes$gene_id %in% ago$ensembl_gene_id)

[1] 116

sum(gvc.genes$gene_id %in% otensg$ensembl_gene_id)

[1] 405

Arrange by Agora’s genetics_score and OpenTargets’ otGeneticsPortal:

d1 <- gvc.genes |>
  left_join(ago, by = join_by(gene_id == ensembl_gene_id)) |> 
  left_join(otensg, by = join_by(gene_id == ensembl_gene_id)) |> 
  arrange(desc(genetics_score), desc(otGeneticsPortal)) |> 
  select(-c(symbol, hgnc_symbol)) |> 
  select(gene_id, gene_symbol, genetics_score, otGeneticsPortal, everything())

d1

Arrange by OpenTargets’ otGeneticsPortal and Agora’s genetics_score:

gvc.genes |>
  left_join(ago, by = join_by(gene_id == ensembl_gene_id)) |> 
  left_join(otensg, by = join_by(gene_id == ensembl_gene_id)) |> 
  arrange(desc(otGeneticsPortal), desc(genetics_score)) |> 
  select(-c(symbol, hgnc_symbol)) |> 
  select(gene_id, gene_symbol, otGeneticsPortal, genetics_score, everything())

Arrange by Agora’s target_risk_score and OpenTargets’ globalScore:

gvc.genes |>
  left_join(ago, by = join_by(gene_id == ensembl_gene_id)) |> 
  left_join(otensg, by = join_by(gene_id == ensembl_gene_id)) |> 
  arrange(desc(target_risk_score), desc(globalScore)) |> 
  select(-c(symbol, hgnc_symbol)) |> 
  select(gene_id, gene_symbol, target_risk_score, globalScore, everything())

Arrange by OpenTargets’ globalScore and Agora’s target_risk_score:

gvc.genes |>
  left_join(ago, by = join_by(gene_id == ensembl_gene_id)) |> 
  left_join(otensg, by = join_by(gene_id == ensembl_gene_id)) |> 
  arrange(desc(globalScore), desc(target_risk_score)) |> 
  select(-c(symbol, hgnc_symbol)) |> 
  select(gene_id, gene_symbol, globalScore, target_risk_score, everything())

Overlap between GVC genes and Agora and OpenTargets genes

x = list(
  "GVC" = gvc.genes$gene_id,
  "Agora" = ago$ensembl_gene_id,
  "OpenTargets" = otensg$ensembl_gene_id
)

library(VennDiagram)
grid.newpage()
v <- venn.diagram(
  x,
  fill = c("#FF0000", "#00FF00", "#0000FF"),
  filename = NULL)
grid.draw(v)

p <- get.venn.partitions(x)
p

Perform ORA of overlap genes

GVC ∩ Agora ∩ OpenTargets

query <- p |> 
  filter(..set.. == "GVC∩Agora∩OpenTargets") |>
  unnest(..values..) |>
  select(gene_id = ..values..) |>
  left_join(ago, by = join_by(gene_id == ensembl_gene_id)) |> 
  left_join(otensg, by = join_by(gene_id == ensembl_gene_id)) |> 
  arrange(desc(genetics_score), desc(otGeneticsPortal)) |> 
  distinct(gene_id) |>
  pull(gene_id)

gostres <- gost(query = query,
                organism = "hsapiens",
                domain_scope = "annotated",
                exclude_iea = TRUE,
                ordered_query = TRUE,
                significant = TRUE,
                user_threshold = 0.005,
                correction_method = "fdr")

gostres$result |> select(term_name, term_id, source, everything())

gostplot(gostres, capped = FALSE, interactive = TRUE)

# save overlap gene ids for later
overlap_gene_ids <- query

GVC ∩ Agora

query <- p |> 
  filter(..set.. %in% c("GVC∩Agora∩OpenTargets", "(GVC∩Agora)∖(OpenTargets)")) |>
  unnest(..values..) |>
  select(gene_id = ..values..) |>
  left_join(ago, by = join_by(gene_id == ensembl_gene_id)) |> 
  left_join(otensg, by = join_by(gene_id == ensembl_gene_id)) |> 
  arrange(desc(genetics_score), desc(otGeneticsPortal)) |> 
  distinct(gene_id) |>
  pull(gene_id)

gostres <- gost(query = query,
                organism = "hsapiens",
                domain_scope = "annotated",
                exclude_iea = TRUE,
                ordered_query = TRUE,
                significant = TRUE,
                user_threshold = 0.005,
                correction_method = "fdr")

gostres$result |> select(term_name, term_id, source, everything())

gostplot(gostres, capped = FALSE, interactive = TRUE)

GVC ∩ OpenTargets

query <- p |> 
  filter(..set.. %in% c("GVC∩Agora∩OpenTargets", "(GVC∩OpenTargets)∖(Agora)")) |>
  unnest(..values..) |>
  select(gene_id = ..values..) |>
  left_join(ago, by = join_by(gene_id == ensembl_gene_id)) |> 
  left_join(otensg, by = join_by(gene_id == ensembl_gene_id)) |> 
  arrange(desc(genetics_score), desc(otGeneticsPortal)) |> 
  distinct(gene_id) |>
  pull(gene_id)

gostres <- gost(query = query,
                organism = "hsapiens",
                domain_scope = "annotated",
                exclude_iea = TRUE,
                ordered_query = TRUE,
                significant = TRUE,
                user_threshold = 0.005,
                correction_method = "fdr")

gostres$result |> select(term_name, term_id, source, everything())

gostplot(gostres, capped = FALSE, interactive = TRUE)

Agora ∩ OpenTargets

query <- p |> 
  filter(..set.. %in% c("GVC∩Agora∩OpenTargets", "(Agora∩OpenTargets)∖(GVC)")) |>
  unnest(..values..) |>
  select(gene_id = ..values..) |>
  left_join(ago, by = join_by(gene_id == ensembl_gene_id)) |> 
  left_join(otensg, by = join_by(gene_id == ensembl_gene_id)) |> 
  arrange(desc(genetics_score), desc(otGeneticsPortal)) |> 
  distinct(gene_id) |>
  pull(gene_id)

gostres <- gost(query = query,
                organism = "hsapiens",
                domain_scope = "annotated",
                exclude_iea = TRUE,
                ordered_query = TRUE,
                significant = TRUE,
                user_threshold = 0.005,
                correction_method = "fdr")

gostres$result |> select(term_name, term_id, source, everything())

gostplot(gostres, capped = FALSE, interactive = TRUE)

(GVC ∩ Agora) ∪ (GVC ∩ OpenTargets) ∪ (Agora ∩ OpenTargets)

query <- p |> 
  filter(..set.. %in% c("GVC∩Agora∩OpenTargets", "(GVC∩Agora)∖(OpenTargets)", "(GVC∩OpenTargets)∖(Agora)", "(Agora∩OpenTargets)∖(GVC)")) |>
  unnest(..values..) |>
  select(gene_id = ..values..) |>
  left_join(ago, by = join_by(gene_id == ensembl_gene_id)) |> 
  left_join(otensg, by = join_by(gene_id == ensembl_gene_id)) |> 
  arrange(desc(genetics_score), desc(otGeneticsPortal)) |> 
  distinct(gene_id) |>
  pull(gene_id)

gostres <- gost(query = query,
                organism = "hsapiens",
                domain_scope = "annotated",
                exclude_iea = TRUE,
                ordered_query = TRUE,
                significant = TRUE,
                user_threshold = 0.005,
                correction_method = "fdr")

gostres$result |> select(term_name, term_id, source, everything())

gostplot(gostres, capped = FALSE, interactive = TRUE)

(Agora ∩ OpenTargets) ∖ (GVC)

query <- p |>
  filter(..set.. == "(Agora∩OpenTargets)∖(GVC)") |> 
  unnest(..values..) |>
  select(gene_id = ..values..) |>
  left_join(ago, by = join_by(gene_id == ensembl_gene_id)) |> 
  left_join(otensg, by = join_by(gene_id == ensembl_gene_id)) |> 
  arrange(desc(genetics_score), desc(otGeneticsPortal)) |> 
  distinct(gene_id) |>
  pull(gene_id)

gostres <- gost(query = query,
                organism = "hsapiens",
                domain_scope = "annotated",
                exclude_iea = TRUE,
                ordered_query = TRUE,
                significant = TRUE,
                user_threshold = 0.005,
                correction_method = "fdr")

gostres$result |> select(term_name, term_id, source, everything())

gostplot(gostres, capped = FALSE, interactive = TRUE)

(GVC ∩ OpenTargets) ∖ (Agora)

query <- p |>
  filter(..set.. == "(GVC∩OpenTargets)∖(Agora)") |> 
  unnest(..values..) |>
  select(gene_id = ..values..) |>
  left_join(ago, by = join_by(gene_id == ensembl_gene_id)) |> 
  left_join(otensg, by = join_by(gene_id == ensembl_gene_id)) |> 
  arrange(desc(genetics_score), desc(otGeneticsPortal)) |> 
  distinct(gene_id) |>
  pull(gene_id)

gostres <- gost(query = query,
                organism = "hsapiens",
                domain_scope = "annotated",
                exclude_iea = TRUE,
                ordered_query = TRUE,
                significant = TRUE,
                user_threshold = 0.005,
                correction_method = "fdr")

gostres$result |> select(term_name, term_id, source, everything())

gostplot(gostres, capped = FALSE, interactive = TRUE)

(OpenTargets) ∖ (GVC ∪ Agora)

query <- p |>
  filter(..set.. == "(OpenTargets)∖(GVC∪Agora)") |> 
  unnest(..values..) |>
  select(gene_id = ..values..) |>
  left_join(ago, by = join_by(gene_id == ensembl_gene_id)) |> 
  left_join(otensg, by = join_by(gene_id == ensembl_gene_id)) |> 
  arrange(desc(genetics_score), desc(otGeneticsPortal)) |> 
  distinct(gene_id) |>
  pull(gene_id)

gostres <- gost(query = query,
                organism = "hsapiens",
                domain_scope = "annotated",
                exclude_iea = TRUE,
                ordered_query = TRUE,
                significant = TRUE,
                user_threshold = 0.005,
                correction_method = "fdr")

gostres$result |> select(term_name, term_id, source, everything())

gostplot(gostres, capped = FALSE, interactive = TRUE)

(GVC ∩ Agora) ∖ (OpenTargets)

query <- p |>
  filter(..set.. == "(GVC∩Agora)∖(OpenTargets)") |> 
  unnest(..values..) |>
  select(gene_id = ..values..) |>
  left_join(ago, by = join_by(gene_id == ensembl_gene_id)) |> 
  left_join(otensg, by = join_by(gene_id == ensembl_gene_id)) |> 
  arrange(desc(genetics_score), desc(otGeneticsPortal)) |> 
  distinct(gene_id) |>
  pull(gene_id)

gostres <- gost(query = query,
                organism = "hsapiens",
                domain_scope = "annotated",
                exclude_iea = TRUE,
                ordered_query = TRUE,
                significant = TRUE,
                user_threshold = 0.005,
                correction_method = "fdr")

gostres$result |> select(term_name, term_id, source, everything())

gostplot(gostres, capped = FALSE, interactive = TRUE)

(Agora) ∖ (GVC ∪ OpenTargets)

query <- p |>
  filter(..set.. == "(Agora)∖(GVC∪OpenTargets)") |> 
  unnest(..values..) |>
  select(gene_id = ..values..) |>
  left_join(ago, by = join_by(gene_id == ensembl_gene_id)) |> 
  left_join(otensg, by = join_by(gene_id == ensembl_gene_id)) |> 
  arrange(desc(genetics_score), desc(otGeneticsPortal)) |> 
  distinct(gene_id) |>
  pull(gene_id)

gostres <- gost(query = query,
                organism = "hsapiens",
                domain_scope = "annotated",
                exclude_iea = TRUE,
                ordered_query = TRUE,
                significant = TRUE,
                user_threshold = 0.005,
                correction_method = "fdr")

gostres$result |> select(term_name, term_id, source, everything())

gostplot(gostres, capped = FALSE, interactive = TRUE)

(GVC) ∖ (Agora ∪ OpenTargets)

query <- p |>
  filter(..set.. == "(GVC)∖(Agora∪OpenTargets)") |> 
  unnest(..values..) |>
  select(gene_id = ..values..) |>
  left_join(ago, by = join_by(gene_id == ensembl_gene_id)) |> 
  left_join(otensg, by = join_by(gene_id == ensembl_gene_id)) |> 
  arrange(desc(genetics_score), desc(otGeneticsPortal)) |> 
  distinct(gene_id) |>
  pull(gene_id)

gostres <- gost(query = query,
                organism = "hsapiens",
                domain_scope = "annotated",
                exclude_iea = TRUE,
                ordered_query = TRUE,
                significant = TRUE,
                user_threshold = 0.005,
                correction_method = "fdr")

gostres$result |> select(term_name, term_id, source, everything())

gostplot(gostres, capped = FALSE, interactive = TRUE)

Perform ORA of GVC genes sorted by Agora or OpenTargets genetics scores

Agora

query <- d1 |> arrange(desc(genetics_score)) |> distinct(gene_id) |> pull(gene_id)

gostres <- gost(query = query,
                organism = "hsapiens",
                domain_scope = "annotated",
                exclude_iea = TRUE,
                ordered_query = TRUE,
                significant = TRUE,
                user_threshold = 0.005,
                correction_method = "fdr")

gostres$result |> select(term_name, term_id, source, everything())

gostplot(gostres, capped = FALSE, interactive = TRUE)

OpenTargets

query <- d1 |> arrange(desc(otGeneticsPortal)) |> distinct(gene_id) |> pull(gene_id)

gostres <- gost(query = query,
                organism = "hsapiens",
                domain_scope = "annotated",
                exclude_iea = TRUE,
                ordered_query = TRUE,
                significant = TRUE,
                user_threshold = 0.005,
                correction_method = "fdr")

gostres$result |> select(term_name, term_id, source, everything())

gostplot(gostres, capped = FALSE, interactive = TRUE)

Correlation of Agora and OpenTargets scores in GVC genes

d1 |> nrow()

[1] 1345

d1 |> drop_na(genetics_score, otGeneticsPortal) |> nrow()

[1] 56

d1 |> drop_na(genetics_score, otGeneticsPortal) |>
  summarize(cor = tidy(cor.test(genetics_score, otGeneticsPortal, method="kendall"))) |>
  unnest(cor)

d1 |> nrow()

[1] 1345

d1 |> drop_na(target_risk_score, globalScore) |> nrow()

[1] 75

d1 |> drop_na(target_risk_score, globalScore) |>
  summarize(cor = tidy(cor.test(target_risk_score, globalScore, method="kendall"))) |>
  unnest(cor)

Correlation of Agora and OpenTargets scores overall

d2 <- ago |> 
  left_join(otensg, by = "ensembl_gene_id") |> 
  arrange(desc(genetics_score), desc(otGeneticsPortal))

d2

d2 |> nrow()

[1] 926

d2 |> drop_na(genetics_score, otGeneticsPortal) |> nrow()

[1] 75

d2 |> drop_na(genetics_score, otGeneticsPortal) |>
  summarize(cor = tidy(cor.test(genetics_score, otGeneticsPortal, method="kendall"))) |>
  unnest(cor)

d2 |> nrow()

[1] 926

d2 |> drop_na(target_risk_score, globalScore) |> nrow()

[1] 484

d2 |> drop_na(target_risk_score, globalScore) |>
  summarize(cor = tidy(cor.test(target_risk_score, globalScore, method="kendall"))) |>
  unnest(cor)

Print environment

sessioninfo::session_info()

─ Session info ───────────────────────────────────────────────────────────────
 setting  value
 version  R version 4.4.1 (2024-06-14)
 os       macOS Sonoma 14.5
 system   aarch64, darwin20
 ui       X11
 language (EN)
 collate  en_US.UTF-8
 ctype    en_US.UTF-8
 tz       America/New_York
 date     2024-07-10
 pandoc   3.1.11 @ /Applications/RStudio.app/Contents/Resources/app/quarto/bin/tools/aarch64/ (via rmarkdown)

─ Packages ───────────────────────────────────────────────────────────────────
 package        * version   date (UTC) lib source
 backports        1.5.0     2024-05-23 [1] CRAN (R 4.4.0)
 bit              4.0.5     2022-11-15 [1] CRAN (R 4.4.0)
 bit64            4.0.5     2020-08-30 [1] CRAN (R 4.4.0)
 bitops           1.0-7     2021-04-24 [1] CRAN (R 4.4.0)
 broom          * 1.0.6     2024-05-17 [1] CRAN (R 4.4.0)
 cellranger       1.1.0     2016-07-27 [1] CRAN (R 4.4.0)
 cli              3.6.3     2024-06-21 [1] CRAN (R 4.4.0)
 colorspace       2.1-0     2023-01-23 [1] CRAN (R 4.4.0)
 crayon           1.5.3     2024-06-20 [1] CRAN (R 4.4.0)
 crosstalk        1.2.1     2023-11-23 [1] CRAN (R 4.4.0)
 data.table       1.15.4    2024-03-30 [1] CRAN (R 4.4.0)
 digest           0.6.36    2024-06-23 [1] CRAN (R 4.4.0)
 dplyr          * 1.1.4     2023-11-17 [1] CRAN (R 4.4.0)
 evaluate         0.24.0    2024-06-10 [1] CRAN (R 4.4.0)
 fansi            1.0.6     2023-12-08 [1] CRAN (R 4.4.0)
 fastmap          1.2.0     2024-05-15 [1] CRAN (R 4.4.0)
 forcats        * 1.0.0     2023-01-29 [1] CRAN (R 4.4.0)
 formatR          1.14      2023-01-17 [1] CRAN (R 4.4.0)
 futile.logger  * 1.4.3     2016-07-10 [1] CRAN (R 4.4.0)
 futile.options   1.0.1     2018-04-20 [1] CRAN (R 4.4.0)
 generics         0.1.3     2022-07-05 [1] CRAN (R 4.4.0)
 ggplot2        * 3.5.1     2024-04-23 [1] CRAN (R 4.4.0)
 glue             1.7.0     2024-01-09 [1] CRAN (R 4.4.0)
 gprofiler2     * 0.2.3     2024-02-23 [1] CRAN (R 4.4.0)
 gtable           0.3.5     2024-04-22 [1] CRAN (R 4.4.0)
 hms              1.1.3     2023-03-21 [1] CRAN (R 4.4.0)
 htmltools        0.5.8.1   2024-04-04 [1] CRAN (R 4.4.0)
 htmlwidgets      1.6.4     2023-12-06 [1] CRAN (R 4.4.0)
 httpuv           1.6.15    2024-03-26 [1] CRAN (R 4.4.0)
 httr             1.4.7     2023-08-15 [1] CRAN (R 4.4.0)
 janitor        * 2.2.0     2023-02-02 [1] CRAN (R 4.4.0)
 jsonlite       * 1.8.8     2023-12-04 [1] CRAN (R 4.4.0)
 knitr            1.47      2024-05-29 [1] CRAN (R 4.4.0)
 labeling         0.4.3     2023-08-29 [1] CRAN (R 4.4.0)
 lambda.r         1.2.4     2019-09-18 [1] CRAN (R 4.4.0)
 later            1.3.2     2023-12-06 [1] CRAN (R 4.4.0)
 lazyeval         0.2.2     2019-03-15 [1] CRAN (R 4.4.0)
 lifecycle        1.0.4     2023-11-07 [1] CRAN (R 4.4.0)
 lubridate      * 1.9.3     2023-09-27 [1] CRAN (R 4.4.0)
 magrittr         2.0.3     2022-03-30 [1] CRAN (R 4.4.0)
 mime             0.12      2021-09-28 [1] CRAN (R 4.4.0)
 munsell          0.5.1     2024-04-01 [1] CRAN (R 4.4.0)
 pillar           1.9.0     2023-03-22 [1] CRAN (R 4.4.0)
 pkgconfig        2.0.3     2019-09-22 [1] CRAN (R 4.4.0)
 plotly           4.10.4    2024-01-13 [1] CRAN (R 4.4.0)
 promises         1.3.0     2024-04-05 [1] CRAN (R 4.4.0)
 purrr          * 1.0.2     2023-08-10 [1] CRAN (R 4.4.0)
 R6               2.5.1     2021-08-19 [1] CRAN (R 4.4.0)
 Rcpp             1.0.12    2024-01-09 [1] CRAN (R 4.4.0)
 RCurl            1.98-1.14 2024-01-09 [1] CRAN (R 4.4.0)
 readr          * 2.1.5     2024-01-10 [1] CRAN (R 4.4.0)
 readxl         * 1.4.3     2023-07-06 [1] CRAN (R 4.4.0)
 rlang            1.1.4     2024-06-04 [1] CRAN (R 4.4.0)
 rmarkdown        2.27      2024-05-17 [1] CRAN (R 4.4.0)
 rstudioapi       0.16.0    2024-03-24 [1] CRAN (R 4.4.0)
 scales           1.3.0     2023-11-28 [1] CRAN (R 4.4.0)
 sessioninfo      1.2.2     2021-12-06 [1] CRAN (R 4.4.0)
 shiny            1.8.1.1   2024-04-02 [1] CRAN (R 4.4.0)
 snakecase        0.11.1    2023-08-27 [1] CRAN (R 4.4.0)
 stringi          1.8.4     2024-05-06 [1] CRAN (R 4.4.0)
 stringr        * 1.5.1     2023-11-14 [1] CRAN (R 4.4.0)
 tibble         * 3.2.1     2023-03-20 [1] CRAN (R 4.4.0)
 tidyr          * 1.3.1     2024-01-24 [1] CRAN (R 4.4.0)
 tidyselect       1.2.1     2024-03-11 [1] CRAN (R 4.4.0)
 tidyverse      * 2.0.0     2023-02-22 [1] CRAN (R 4.4.0)
 timechange       0.3.0     2024-01-18 [1] CRAN (R 4.4.0)
 tzdb             0.4.0     2023-05-12 [1] CRAN (R 4.4.0)
 utf8             1.2.4     2023-10-22 [1] CRAN (R 4.4.0)
 vctrs            0.6.5     2023-12-01 [1] CRAN (R 4.4.0)
 VennDiagram    * 1.7.3     2022-04-12 [1] CRAN (R 4.4.0)
 viridisLite      0.4.2     2023-05-02 [1] CRAN (R 4.4.0)
 vroom            1.6.5     2023-12-05 [1] CRAN (R 4.4.0)
 withr            3.0.0     2024-01-16 [1] CRAN (R 4.4.0)
 xfun             0.45      2024-06-16 [1] CRAN (R 4.4.0)
 xtable           1.8-4     2019-04-21 [1] CRAN (R 4.4.0)
 yaml             2.3.8     2023-12-11 [1] CRAN (R 4.4.0)

 [1] /Users/marcoe02/.Rlib
 [2] /Library/Frameworks/R.framework/Versions/4.4-arm64/Resources/library

──────────────────────────────────────────────────────────────────────────────